Paper Citation Record · LEDGER

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model

As of 16 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2607.22083.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.22083 v2

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T05:54:58.505989Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

34 of 34 outbound references displayed

verified exact0
verified fuzzy0
unresolved34
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0dd0c917-cbe4-4bde-9a2e-efa5048017fe · outbound

This paper cites Program Synthesis with Large Language Models.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Program Synthesis with Large Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:55.645402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adbad365-652e-4887-84a2-f4c60562b031 · outbound

This paper cites Mixture-of-recursions: Learning dy- namic recursive depths for adaptive token-level computation.Advances in Neural Information Processing Systems, 38:96572–96617, 2026.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Mixture-of-recursions: Learning dy- namic recursive depths for adaptive token-level computation.Advances in Neural Information Processing Systems, 38:96572–96617, 2026

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:55.695985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bee74f9-5a90-4f73-8fd9-0b228c35d735 · outbound

This paper cites ClawGym: A Scalable Framework for Building Effective Claw Agents.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model ClawGym: A Scalable Framework for Building Effective Claw Agents

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:55.759897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db7e715e-d7ba-4bcc-8923-afbd67c5e33c · outbound

This paper cites MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:55.840115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6359b7c5-0bc4-4341-bb71-c427100b2ac7 · outbound

This paper cites Agentif-oneday: A task-level instruction-following benchmark for general ai agents in daily scenarios, 2026.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Agentif-oneday: A task-level instruction-following benchmark for general ai agents in daily scenarios, 2026

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:55.907441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f98e4b8e-0778-431f-8fbc-25925a61a626 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Training Verifiers to Solve Math Word Problems

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:55.971166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57b9d118-af38-47e3-9a6b-8af37fb786e6 · outbound

This paper cites Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:56.049451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0fba175-a3c8-473e-96c6-e992ec935c79 · outbound

This paper cites SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:56.125487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c60a8523-ab81-4d0e-b09a-df04d2e70e60 · outbound

This paper cites Supergpqa: Scaling llm evaluation across 285 graduate disciplines.Advances in Neural Information Processing Systems, 38, 2026.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Supergpqa: Scaling llm evaluation across 285 graduate disciplines.Advances in Neural Information Processing Systems, 38, 2026

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:56.176875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 958e467e-2bd0-4dc8-8505-cd783b4e15a0 · outbound

This paper cites GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:56.231056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1a48bf7-fac9-4b4d-819a-ddc839675613 · outbound

This paper cites Tmax: A simple recipe for terminal agents.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Tmax: A simple recipe for terminal agents

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:56.305142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6947021a-c2bf-402c-85a7-5490e798b83c · outbound

This paper cites Livecodebench: Holistic and contamination free evaluation of large language models for code, 2024.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Livecodebench: Holistic and contamination free evaluation of large language models for code, 2024

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:56.369643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85b83d99-d3d0-42f2-a757-f92f16962392 · outbound

This paper cites Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:56.401350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f6a163d-e189-4315-a8e0-8bece363d9a8 · outbound

This paper cites Deepresearch bench ii: Diagnosing deep research agents via rubrics from expert reports.arXiv preprint arXiv:2601.08536, 2026.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Deepresearch bench ii: Diagnosing deep research agents via rubrics from expert reports.arXiv preprint arXiv:2601.08536, 2026

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:56.477243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a62cdaaf-7b10-408a-b5c3-c6317e5dfe0c · outbound

This paper cites Towards robust mathematical reasoning.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Towards robust mathematical reasoning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:56.564898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b070c7f2-babc-416e-a05f-0b22a933920f · outbound

This paper cites Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:56.637734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6592d398-404e-47a5-96e1-786c7ff2a7d5 · outbound

This paper cites Officeqa pro: An enterprise benchmark for end-to-end grounded reasoning.arXiv preprint arXiv:2603.08655, 2026.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Officeqa pro: An enterprise benchmark for end-to-end grounded reasoning.arXiv preprint arXiv:2603.08655, 2026

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:56.757815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7fd285d-1388-48a3-a83d-14b85f3528dc · outbound

This paper cites Humanity’s last exam, 2025.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Humanity’s last exam, 2025

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:56.843445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3c41f4e-4dfb-4b40-9e38-7662dc2261cf · outbound

This paper cites Generalizing verifiable instruction following.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Generalizing verifiable instruction following

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:56.914670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c80221f-9ace-4261-b7ca-649787788bc4 · outbound

This paper cites Qwen3.5: Towards native multimodal agents, February 2026.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Qwen3.5: Towards native multimodal agents, February 2026

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:57.005356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 219fd648-6f42-4f13-a040-633c026eb5a9 · outbound

This paper cites an unresolved cited work.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:57.097733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ddacccd-df28-4018-a6dd-c8b09ded60f3 · outbound

This paper cites Hendryx, Brad Kenstler, and Bing Liu.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Hendryx, Brad Kenstler, and Bing Liu

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:57.218915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b605d3db-def9-4d51-8e8c-1dba1e171b56 · outbound

This paper cites Openclaw: Your own personal ai assistant, 2026.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Openclaw: Your own personal ai assistant, 2026

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:57.316169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d531102-12ae-4482-abc7-de5ac683fa34 · outbound

This paper cites Challenging big- bench tasks and whether chain-of-thought can solve them.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Challenging big- bench tasks and whether chain-of-thought can solve them

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:57.412181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea29f70f-2007-416c-9ab5-5a98f03651eb · outbound

This paper cites Gemma 4 Technical Report.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Gemma 4 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:57.534939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb2119bc-451c-481e-9a90-000e7e86d91b · outbound

This paper cites Scicode: A research coding benchmark curated by scientists.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Scicode: A research coding benchmark curated by scientists

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:57.623108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3c3b7e8-217f-4c78-a1b0-5abdc9ccaa03 · outbound

This paper cites Mmlu-pro: A more robust and challenging multi-task language understanding benchmark.Advances in Neural Information Processing Systems, 37:95266–95290, 2024.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Mmlu-pro: A more robust and challenging multi-task language understanding benchmark.Advances in Neural Information Processing Systems, 37:95266–95290, 2024

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:57.698486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60414289-0ba2-4c05-b296-253acca45852 · outbound

This paper cites Vibethinker-3b: Exploring the frontier of verifiable reasoning in small language models.arXiv preprint arXiv:2606.16140, 2026.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Vibethinker-3b: Exploring the frontier of verifiable reasoning in small language models.arXiv preprint arXiv:2606.16140, 2026

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:57.809388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acc48075-4dba-41cf-ac7f-cb90951774e5 · outbound

This paper cites Toolmind technical report: A large-scale, reasoning-enhanced tool-use dataset.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Toolmind technical report: A large-scale, reasoning-enhanced tool-use dataset

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:57.897424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4358f851-d70f-4ba8-a079-b20307487d0c · outbound

This paper cites Nanbeige4-3b technical report: Exploring the frontier of small language models.arXiv preprint arXiv:2512.06266, 2025.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Nanbeige4-3b technical report: Exploring the frontier of small language models.arXiv preprint arXiv:2512.06266, 2025

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:58.009577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 274e200a-1e4b-42bd-8f02-e73f15aef5fd · outbound

This paper cites Nanbeige4.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Nanbeige4

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:58.132481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ada1b16-7450-4449-85c3-11b3e74a6c93 · outbound

This paper cites Iquest-coder-v1 technical report.arXiv preprint arXiv:2603.16733, 2026.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Iquest-coder-v1 technical report.arXiv preprint arXiv:2603.16733, 2026

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:58.258415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a20468aa-4269-4a38-800f-207c5c8c3112 · outbound

This paper cites Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:58.383145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9e9fde6-1051-40ed-b35e-2049040aeaa4 · outbound

This paper cites Scaling Latent Reasoning via Looped Language Models.

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model Scaling Latent Reasoning via Looped Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T05:54:58.505989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.